language model

NSF-SciFy: Mining the NSF Awards Database for Scientific Claims ACL 2026 Octopus: Entropy-Controlled Science Fiction Literature Generation with Persistent Memory-Context Binding AAAI 2026 OneFont: A Unified Agent for End-to-End Font Creation AAAI 2026 On the Emergence and Test-Time Use of Structural Information in Large Language Models ACL 2026 Open-Domain Safety Policy Construction EACL 2026 Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules EACL 2026 PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering ACL 2026 Pinetree at SemEval-2026 Task 7: A Large-Scale Failure Analysis of Cultural Grounding in Language Models SemEval 2026 Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios EACL 2026 Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL Estimator AAAI 2026 Pretraining Language Models for Diachronic Linguistic Change Discovery EACL 2026 Probing for Reading Times ACL 2026 Pushing the Frontiers of Scientific Fact-Checking: The SCINLP Dataset EACL 2026 ReCode: Updating Code API Knowledge with Reinforcement Learning AAAI 2026 Redefining Retrieval Evaluation in the Era of LLMs EACL 2026 RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models EACL 2026 Rethinking Deep Alignment Through the Lens of Incomplete Safety Learning AAAI 2026 Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety EACL 2026 RetrySQL: Text-to-SQL Training with Retry Data for Self-Correcting Query Generation AAAI 2026 Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths EACL 2026 Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment COLT 2026 Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models EACL 2026 RTMol: Rethinking Molecule-text Alignment in a Round-trip View AAAI 2026 Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026